CN115659929A - Multi-document-based annotation interaction method and system - Google Patents
Multi-document-based annotation interaction method and system Download PDFInfo
- Publication number
- CN115659929A CN115659929A CN202211301753.7A CN202211301753A CN115659929A CN 115659929 A CN115659929 A CN 115659929A CN 202211301753 A CN202211301753 A CN 202211301753A CN 115659929 A CN115659929 A CN 115659929A
- Authority
- CN
- China
- Prior art keywords
- information
- annotation
- user
- port
- document
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Document Processing Apparatus (AREA)
Abstract
The invention provides a comment interaction method and system based on multiple documents, which relate to the technical field of computer information processing, and are used for obtaining multiple-document comment information, extracting a comment user source, generating a label for comment marking, screening the multiple-document comment information based on port user information, obtaining comment information to be consulted, inputting a comment record set of port users into a comment analysis model, obtaining port user comment characteristics, further carrying out identification conversion on the comment information to be consulted, and displaying through the displayed port information.
Description
Technical Field
The invention relates to the technical field of computer information processing, in particular to a comment interaction method and system based on multiple documents.
Background
At present, accessible terminal display device reads the document at any time, when analyzing the notes that appear in the document, can only judge through artifical comparative analysis at present, because the subjectivity of individual notes custom and semantic understanding, make the document reading process comparatively loaded down with trivial details, reading inefficiency, the wrong situation of judgement can appear simultaneously, the accessible carries out the conversion of notes mode and notes content to the document notes, improve the degree of agreeing with of document notes mode and look up the user, however when carrying out notes information processing, because prior art's limitation, make final processing result can't reach anticipated standard, prior art still has certain promotion space.
In the prior art, when document annotation consulting is carried out, because the processing method of annotation information is not intelligent enough, and the diversity of annotation modes and the subjective assumption of consultants, the document consulting efficiency is low and the risk of analytic deviation exists.
Disclosure of Invention
The application provides a comment interaction method and system based on multiple documents, which are used for solving the technical problems that in the prior art, a comment information processing method is not intelligent enough, and the document consulting efficiency is low and the risk of analytic deviation exists due to the diversity of comment modes and the subjective assumption of information of consultants.
In view of the above problems, the present application provides a method and a system for annotation interaction based on multiple documents.
In a first aspect, the present application provides a multi-document-based annotation interaction method, including: obtaining multi-document information; identifying multi-document annotation information based on the multi-document information, wherein the multi-document annotation information comprises an annotation position and annotation document reference content; extracting the source of the annotation user according to the multi-document annotation information, determining the annotation user information, and generating a label based on the annotation user information to label the multi-document annotation information; acquiring display port information, and determining port user information based on the display port information; according to the port user information, performing annotation user information screening on the multi-document annotation information to obtain annotation information to be consulted, wherein the annotation information to be consulted comprises annotation reply information of a port user and annotation information of a non-port user; acquiring an annotation record set of a port user, inputting the annotation record set of the port user into an annotation analysis model, and acquiring annotation characteristics of the port user; and identifying and converting the annotation information to be consulted based on the port user annotation characteristics, and displaying through the display port information.
In a second aspect, the present application provides a multi-document-based annotation interaction system, which includes: the information acquisition module is used for acquiring multi-document information; the information identification module is used for identifying multi-document annotation information based on the multi-document information, wherein the multi-document annotation information comprises an annotation position and annotation document reference content; the information labeling module is used for extracting a source of a comment user according to the multi-document comment information, determining the comment user information and generating a label based on the comment user information to label the multi-document comment information; the information determining module is used for obtaining display port information and determining port user information based on the display port information; the information screening module is used for screening the multi-document annotation information according to the port user information to obtain annotation information to be consulted, wherein the annotation information to be consulted comprises annotation reply information of the port user and non-port user annotation information; the system comprises a characteristic acquisition module, a comment analysis module and a comment analysis module, wherein the characteristic acquisition module is used for acquiring a comment record set of a port user, inputting the comment record set of the port user into a comment analysis model and acquiring the comment characteristics of the port user; and the information conversion module is used for identifying and converting the annotation information to be consulted based on the port user annotation characteristics and displaying the annotation information through the display port.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the annotation interaction method based on the multiple documents, provided by the embodiment of the application, comprises the steps of obtaining multiple document information and identifying annotation information, wherein the annotation information comprises annotation positions and annotation document reference contents, the annotation user source extraction is carried out to determine annotation user information, a label is generated to label the multiple document annotation information, display port information is obtained, the port user information is determined, the multiple document annotation information is screened, and annotation information to be looked up is obtained and comprises annotation reply information of port users and annotation information of non-port users; inputting the comment record set of the port user into a comment analysis model, obtaining the comment characteristics of the port user, further identifying and converting the comment information to be looked up, displaying the port information, solving the problems that the processing method of the comment information in the prior art is not intelligent enough, and the diversity of comment modes and the subjective assumption of information of consultants cause low document look-up efficiency and the technical problem of analysis deviation risk, carrying out intelligent conversion of document comments based on the comment habits of the consultants, so as to improve the appropriation degree of the document comments and the consultants, and carrying out efficient and accurate look-up of the document.
Drawings
FIG. 1 is a schematic flow chart of a multi-document-based annotation interaction method provided by the present application;
FIG. 2 is a schematic diagram illustrating a recognition and conversion process of annotation information to be referred in an annotation interaction method based on multiple documents according to the present application;
FIG. 3 is a schematic diagram illustrating a process of annotation reply information tagging in a multi-document-based annotation interaction method provided by the present application;
fig. 4 is a schematic structural diagram of a multi-document-based annotation interaction system according to the present application.
Description of reference numerals: the system comprises an information acquisition module 11, an information identification module 12, an information labeling module 13, an information determination module 14, an information screening module 15, a characteristic acquisition module 16 and an information conversion module 17.
Detailed Description
The application provides a multi-document annotation interaction method and system, multi-document annotation information is obtained, annotation user source extraction is carried out, labels are generated for annotation marking, the multi-document annotation information is screened based on port user information, annotation information to be looked up is obtained, annotation records of port users are input into an annotation analysis model, port user annotation characteristics are obtained, identification conversion is carried out on the annotation information to be looked up, and the display port information is displayed, so that the technical problems that in the prior art, the annotation information processing method is not intelligent enough, the information subjective assumption of annotation modes and consultants is poor, document looking-up efficiency is low, and analysis deviation risks exist are solved.
Example one
As shown in fig. 1, the present application provides a multi-document-based annotation interaction method, including:
step S100: obtaining multi-document information;
specifically, at present, document reading can be performed at any time through a terminal display device, but due to subjectivity of individual annotation habits, annotations in a document can only be judged through manual comparative analysis in a reading process, so that reading efficiency is low, and a situation of judgment errors may occur.
Step S200: identifying multi-document annotation information based on the multi-document information, wherein the multi-document annotation information comprises an annotation position and annotation document reference content;
step S300: extracting the source of the annotation user according to the multi-document annotation information, determining the annotation user information, and generating a label based on the annotation user information to label the multi-document annotation information;
further, the obtained multi-document information is subjected to information recognition, a comment position corresponding to each piece of comment information and comment document reference content are determined, wherein the comment position is correspondingly associated with the comment document reference content, optionally, a plurality of different comment users may exist in the recognized comment information, due to different personal comment habits, the corresponding recognition characteristics such as corresponding comment information formats exist differently, the comment users and the corresponding document comment information are correspondingly marked, a comment information marking result is obtained, so that the comment users and the corresponding document comment information are subjected to subsequent recognition and differentiation, targeted processing is performed, the recognized comment information is further subjected to integration processing, and the multi-document comment information is generated.
And further processing the multi-document annotation information, extracting information of the multi-document annotation information based on annotation information identification results, determining annotation users existing in the multi-document annotation information, optionally, extracting annotation sources of the annotation users, determining information such as user names, annotation characteristics and personal styles of the annotation users as the annotation user information, further simplifying and organizing the annotation user information, determining a label capable of reflecting subjective characteristics of the annotation users, and labeling the multi-document annotation information based on the generated label so as to directly perform information identification and conversion according to the labeled label subsequently, and improve information processing efficiency.
Step S400: obtaining display port information, and determining port user information based on the display port information;
step S500: according to the port user information, performing annotation user information screening on the multi-document annotation information to obtain annotation information to be consulted, wherein the annotation information to be consulted comprises annotation reply information of a port user and non-port user annotation information;
specifically, a terminal display device for reading the multi-document information is determined, the terminal display device may be an electronic device such as a computer or a mobile phone, and further extracts information from a display port of the terminal display device, for example, a login user, device display characteristics, a display format, and the like, which is used as the display port information, further extracts user information of the login user, including user identity information, document review content information, and the like, which is used as the port user information, based on the display port information, the port user is a user who is currently performing an operation, and further, based on the port user information, performs annotation user information screening on the multi-document annotation information according to the document review content information, determines annotation information covered by document content which is reviewed by the port user, including annotation reply information of the port user and non-port user annotation information, where the non-port user annotation information may include annotation information of multiple different users, and may be directly identified and determined based on annotated tags, integrates the information to generate the annotation information to be reviewed, and the information to be subsequently obtained is converted into basic review information.
Step S600: acquiring an annotation record set of a port user, inputting the annotation record set of the port user into an annotation analysis model, and acquiring annotation characteristics of the port user;
step S700: and identifying and converting the annotation information to be consulted based on the port user annotation characteristics, and displaying through the display port information.
Specifically, the annotation analysis model is constructed, namely a virtual model for performing annotation information feature recognition analysis is constructed, historical annotation record retrieval is performed on the port user based on reference content and annotation content, an annotation record set of the port user is obtained, then the annotation record set of the port user is used as sample data and is divided into a training set and a verification set, model training and verification are performed on the constructed annotation analysis model until the feature recognition analysis accuracy of the annotation analysis model reaches a preset standard, model training is stopped, the trained model is used as the finally determined annotation analysis model, and meanwhile, the annotation features of the port user can be output.
Further, the annotation characteristics of the port user are determined through model analysis, the annotation characteristics can laterally reflect the annotation habits of the port user, the annotation characteristics are divided to determine various annotation types, such as annotation formats and annotation sequences of important points, keyword annotation modes, meanings of different marks and the like, annotation information of a plurality of pieces of annotation information to be consulted is classified based on the various annotation types of the port user, information conversion is further performed based on the corresponding annotation characteristics, the annotation information to be consulted is converted into the annotation modes conforming to the annotation habits of the port user, so that fluency and consultation efficiency of the port user in document consultation are ensured, the annotation information to be consulted after information conversion is further displayed based on the display port information, the display port information is relevant information of terminal display equipment for document consultation, and information display is performed by performing annotation information conversion on a plurality of document information recognition ports, so that the classifying user can conveniently perform information consultation.
Further, the annotation record set of the port user is input into an annotation analysis model to obtain the annotation characteristics of the port user, and step S600 of the present application further includes:
step S610: according to the annotation record set of the port user, reference content and annotation content are used as input parameters, user annotation characteristics are used as output results, a machine learning model is established, and a training data set is established by using the annotation record set to train and learn the machine learning model;
step S620: and performing feature recognition analysis on the reference content and the annotation content to determine annotation type features, performing annotation format and sentence structure sequence recognition processing based on the annotation type features, and determining the port user annotation features.
Specifically, the port user is called based on big data, the port user is a user who performs operation currently, the reference content in the called annotation record is associated and corresponds to the annotation content, the annotation records of the same type are classified and integrated to generate an annotation record set of the port user, the machine learning model is further constructed based on a machine learning algorithm, the machine learning model is an auxiliary tool for performing input content feature extraction, optionally, the machine learning model can be a multi-level network layer and comprises an information identification layer, a feature comparison analysis layer and an input and output layer, wherein the input layer and the output layer are necessary structures of the model and have no special significance, the annotation record set is used as sample data and is divided into a training set and a verification set, the training set and the verification set are further input into the machine learning model, and model training and verification are performed until the simulation precision of the model reaches a predetermined accuracy, for example, 95%, so as to determine the annotation analysis model.
Furthermore, the quote content and the comment content are input into an information identification layer of the comment analysis model based on an input layer, comment state information is determined, and then the comment state information is transmitted into the characteristic comparison analysis layer, the comment type characteristics, such as characters, graphs, diagrams, transverse lines, numbers and the like, are determined, the expression ideas corresponding to different comment types are different, such as key marks, keyword marks and the like, the comment format is regulated based on the comment type characteristics, the habit of the conventional comment content is determined, exemplarily, the arrangement sequence of the characters, the graphs and the icons, the sentence structure sequence and the like, such as keywords, verbs and the graphs are used as the sequence structure of individual expression, and the comment of the quote content is performed, namely, a label feature word is directly added based on the expression structure and determined as the comment characteristic of the port user, the comment standardized format of the port user is obtained, and meanwhile, the characteristic extraction is performed based on the comment analysis model, so that the accuracy and the objectivity of the output comment characteristic can be effectively guaranteed.
Further, as shown in fig. 2, before performing recognition conversion on the comment information to be referred to based on the port user comment feature, step S700 of the present application further includes:
step S710-1: obtaining the viewing requirement of a port user;
step S720-1: identifying and searching the comment information to be searched according to the checking requirement of the port user, and determining the comment information needing to be checked;
step S730-1: determining the annotation feature type according to the annotation features of the port user, and identifying and matching the annotation information required to be checked based on the annotation feature type to obtain matched annotation information to be converted;
step S740-1: and identifying and converting the matched annotation information to be converted based on the port user annotation characteristics.
Specifically, the multi-document annotation information is screened based on the annotation user information to obtain the annotation information to be consulted, so that the viewing requirements of the port user, namely the current operation user, such as the annotation of document difficulty, are determined, the annotation information to be consulted is further subjected to information identification, the annotation information meeting the viewing requirements of the port user is determined, and the annotation information is used as the requirement viewing annotation information, namely, the annotation information is partial information for ensuring the viewing fluency and having annotation information conversion necessity.
Further, based on the annotation characteristics of the port user, the annotation characteristic types are determined, for example, different annotation format sequences and the like are adopted for different annotation significances, wherein the annotation characteristic types may include multiple types, and then the annotation characteristic types and the demand check annotation information are subjected to information matching, the demand check annotation information corresponding to a matching result and the annotation characteristic types are correspondingly marked so as to be directly identified and distinguished, wherein one annotation characteristic type can correspond to one or more pieces of demand check annotation information, which is used as the matching annotation information to be converted, and further, based on the annotation characteristics of the port user, the matching annotation information to be converted is subjected to information identification conversion according to the corresponding annotation characteristic types, and the document annotation information is converted into the annotation information conforming to the custom annotations of the port user on the basis of not influencing the annotation information content and integrity, so that the document reading smoothness and the annotation comfort level of the port user can be effectively improved, and the subjective analysis deviation of the annotation content can be avoided.
Further, step S700 of the present application further includes:
step S710-2: analyzing the quotation content of the quotation document according to the quotation information to be consulted, and extracting the same-root quotation information set;
step S720-2: analyzing the annotation user information of the same annotation information set to determine the user association degree of the annotation user information and the port user information;
step S730-2: generating different display characteristics based on different user association degrees;
step S740-2: and performing content semantic analysis based on the same-root annotation information set, determining semantic similarity, and performing same-type marking on the annotations with high similarity based on the semantic similarity.
Specifically, annotating and sourcing are respectively performed on a plurality of pieces of annotation information in the annotation information to be consulted, whether annotation document reference content corresponding to the annotation information belongs to the same reference content or not is determined, namely the same reference content or a keyword corresponds to the plurality of pieces of annotation information, and the same-root annotation information set is generated by performing information corresponding integration and annotation, wherein in the same-root annotation information set, the annotation information corresponding to the same reference content may be annotated by the same annotation user or a plurality of different annotation users.
The annotation information set is further analyzed for annotation user information, the annotation user information and the port user information are analyzed for user association degree, for example, the annotation information set has the same annotation and the attention degree of annotation contents, different display features are set based on the difference of the user association degree, the display priority is decreased according to the relevance degree, the display features are more obvious according to the higher relevance degree, furthermore, the annotation information set is subjected to semantic analysis respectively based on the quoted contents, the semantic similarity of the same annotation of each group is determined, the same annotation with higher similarity can be regarded as the annotation with the same type, and optionally, multiple annotation types are set based on the multi-level similarity so as to selectively look up the annotation information, the repeated look-up rate of the information is reduced, and the document look-up efficiency can be effectively improved.
Further, as shown in fig. 3, step S700 of the present application further includes:
step S710-3: when the display port displays the annotation reply information of the port user, performing semantic recognition on the annotation reply information to obtain reply semantic information;
step S720-3: according to the reply semantic information, displaying the same display characteristics of the semantic similarity meeting the preset requirement;
step S730-3: acquiring annotation user information of the annotation reply information;
step S740-3: determining a reply user relationship according to the annotation user information and the port user information;
step S750-3: and marking the annotation reply information of the port user based on the reply user relationship and the semantic similarity.
Specifically, when information conversion is performed on the comment information to be referred, wherein partial comment reply information exists, comment information display is performed based on the display port after the conversion is completed, if the display port displays the comment reply information of the port user, the comment reply information is extracted and subjected to semantic recognition, specific reply content directions such as comment supplement, comment judgment and the like are determined, the comment reply semantic information is further subjected to semantic similarity judgment, a preset requirement can be set, namely a critical value limited by semantic similarity is performed, each piece of information in the reply semantic information is judged to be subjected to pairwise collation analysis respectively, whether the semantic similarity meets the preset requirement is determined, when the preset requirement is met, the two pieces of information to be compared belong to the same-feature semantic information is indicated, the judgment result is further classified and integrated, and the same-feature semantic information is displayed.
Further, obtaining annotation information corresponding to the annotation reply information, and determining annotation user information of the annotation information, wherein the annotation user information, the annotation reply information and the annotation information correspond to each other, analyzing an information reply relationship between the annotation user information and the port user information, and determining the reply user relationship, the annotation user may be an annotation of a port user or other users, the annotation reply information is the port user annotation, classifying, integrating and identifying the annotation reply information of the port user according to the reply user relationship and the semantic similarity, and identifying the same category based on the same identification information, so that the user can check the annotation specifically.
Further, after displaying the same-display feature that the semantic similarity meets the preset requirement according to the reply semantic information, step S720-3 of the present application further includes:
step S721-3: classifying the comment reply information according to the semantic similarity;
step S722-3: determining classification display characteristics based on classification results of the annotation reply information;
step S723-3: and highlighting the semantic similarity lower than a preset threshold value.
Specifically, semantic recognition is performed on the annotation reply information to determine the reply semantic information, semantic similarity analysis is further performed on the reply semantic information, illustratively, a plurality of similarity intervals can be determined by setting a similarity classification interval, the annotation reply information is classified based on the semantic similarity to obtain a classification result of the annotation classification information, classification display features corresponding to classification levels in the classification result are determined, illustratively, interval information with high overlapping degree, namely, the highest similarity is uniformly displayed based on the same display features, displayable non-displayable intervals with general similarity are further set as the preset threshold, namely, a bottom line critical value of the semantic similarity is limited, when the semantic similarity in the classification result is lower than the preset threshold, the corresponding annotation reply information belongs to a unique reply and is highlighted, and by performing classification display on the annotation reply information based on the semantic similarity, targeted information extraction can be performed according to actual consulting requirements, and information recognition efficiency is improved.
Further, step S700 of the present application further includes:
step S710-4: acquiring a checking requirement of an annotation user;
step S720-4: determining checking annotation user information based on the checking requirements of the annotation users, and performing traversal comparison on the multi-document annotation information based on the checking annotation user information to obtain a checking user annotation information set;
step S730-4: analyzing the comment quote content and the comment information of the checked user comment information set to obtain the user concerned content characteristic and the comment information characteristic;
step S740-4: and generating demand display information to be displayed through display port information according to the checking user comment information set, the user attention content characteristics and the comment information characteristics.
Specifically, before document lookup is performed, corresponding document information can be directly determined based on a lookup target requirement to avoid invalid work, a user viewing requirement corresponding to document annotation information is determined, namely the document annotation information is looked up as the annotation user viewing requirement, the user information for viewing the annotation is further determined based on the annotation user viewing requirement as the viewing annotation user information, traversal comparison is further performed on the multi-document annotation information based on the viewing annotation user information, annotation information made by each viewing annotation user information on the document is determined, relevant annotation information and user information are correspondingly integrated to generate a viewing user annotation information set, and multiple sets of annotation information corresponding to different users in the viewing user annotation information set are further identified and analyzed, performing joint analysis based on the annotation quotation content and the annotation information characteristics, performing comprehensive consideration based on the annotation frequency, the annotation direction and the like of quotation content, acquiring the user concerned content characteristics and the annotation information characteristics, further performing information correspondence and joint analysis on the checking user annotation information set, the user concerned content characteristics and the annotation information characteristics, determining the checking required and known content of the document, namely checking requirement information, serving as the requirement display information and performing information display based on the display port, and comprising the display port, namely a display end for information display.
Example two
Based on the same inventive concept as the multi-document-based annotation interaction method in the foregoing embodiment, as shown in fig. 4, the present application provides a multi-document-based annotation interaction system, which includes:
an information obtaining module 11, wherein the information obtaining module 11 is used for obtaining multi-document information;
the information identification module 12 is configured to identify multi-document annotation information based on the multi-document information, where the multi-document annotation information includes an annotation position and annotation document reference content;
the information labeling module 13 is configured to perform annotation user source extraction according to the multi-document annotation information, determine annotation user information, and generate a label based on the annotation user information to label the multi-document annotation information;
an information determining module 14, wherein the information determining module 14 is configured to obtain display port information, and determine port user information based on the display port information;
the information screening module 15 is configured to perform annotation user information screening on the multi-document annotation information according to the port user information to obtain annotation information to be consulted, where the annotation information to be consulted includes annotation reply information of the port user and annotation information of a non-port user;
the feature acquisition module 16 is configured to acquire an annotation record set of the port user, and input the annotation record set of the port user into the annotation analysis model to acquire an annotation feature of the port user;
and the information conversion module 17 is configured to perform identification conversion on the annotation information to be referred based on the port user annotation feature, and display the annotation information through the display port.
Further, the system further comprises:
the request acquisition module is used for acquiring the viewing request of the port user;
the annotation information determining module is used for identifying and searching the annotation information to be searched according to the viewing requirement of the port user and determining the annotation information required to be viewed;
the information matching module is used for determining the annotation feature type according to the annotation features of the port user, identifying and matching the annotation information required to be checked based on the annotation feature type, and obtaining matched annotation information to be converted;
and the information identification conversion module is used for carrying out identification conversion on the matched annotation information to be converted based on the port user annotation characteristics.
Further, the system further comprises:
the citation analysis module is used for analyzing citation content of the annotation document according to the annotation information to be consulted and extracting a same-root annotation information set;
the relevancy determining module is used for analyzing the annotation user information of the same annotation information set and determining the user relevancy between the annotation user information and the port user information;
the display characteristic generation module is used for generating different display characteristics based on different user association degrees;
and the annotation marking module is used for performing content semantic analysis based on the same-root annotation information set, determining semantic similarity, and marking the annotations with high similarity in the same type based on the semantic similarity.
Further, the system further comprises:
the semantic recognition module is used for performing semantic recognition on the annotation reply information when the display port displays the annotation reply information of the port user to obtain the reply semantic information;
the feature display module is used for displaying the same display features of which the semantic similarity meets the preset requirement according to the reply semantic information;
the user information acquisition module is used for acquiring annotation user information of the annotation reply information;
the relationship determination module is used for determining a reply user relationship according to the annotation user information and the port user information;
and the reply information marking module is used for marking the comment reply information of the port user based on the reply user relationship and the semantic similarity.
Further, the system further comprises:
the information classification module is used for classifying the annotation reply information according to the semantic similarity;
the display characteristic determining module is used for annotating the classification result of the reply information and determining the classification display characteristics;
and the threshold judging module is used for highlighting the semantic similarity lower than a preset threshold.
Further, the system further comprises:
the requirement acquisition module is used for acquiring checking requirements of the annotation users;
the information comparison module is used for determining checking annotation user information based on checking requirements of the annotation users, and performing traversal comparison on the multi-document annotation information based on the checking annotation user information to obtain a checking user annotation information set;
the characteristic information acquisition module is used for analyzing comment quotation content and comment information of the review user comment information set to acquire user attention content characteristics and comment information characteristics;
and the information display module is used for generating the required display information according to the checking user comment information set, the user attention content characteristics and the comment information characteristics and displaying the required display information through the display port information.
Further, the system further comprises:
the model building training module is used for building a machine learning model by taking the quote content and the comment content as input parameters and the user comment characteristics as output results according to the comment record set of the port user, and building a training data set by using the comment record set to train and learn the machine learning model;
the annotation feature determination module is used for performing feature recognition analysis on the reference content and the annotation content, determining annotation type features, performing annotation format and sentence structure sequence recognition processing based on the annotation type features, and determining the annotation features of the port user.
Through the foregoing detailed description of the annotation interaction method based on multiple documents, those skilled in the art can clearly know that, in the embodiment, the annotation interaction method and system based on multiple documents are provided.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A multi-document-based annotation interaction method is characterized by comprising the following steps of:
obtaining multi-document information;
identifying multi-document annotation information based on the multi-document information, wherein the multi-document annotation information comprises an annotation position and annotation document reference content;
extracting the source of the annotation user according to the multi-document annotation information, determining the annotation user information, and generating a label based on the annotation user information to label the multi-document annotation information;
obtaining display port information, and determining port user information based on the display port information;
according to the port user information, performing annotation user information screening on the multi-document annotation information to obtain annotation information to be consulted, wherein the annotation information to be consulted comprises annotation reply information of a port user and non-port user annotation information;
acquiring an annotation record set of a port user, inputting the annotation record set of the port user into an annotation analysis model, and acquiring annotation characteristics of the port user;
and identifying and converting the annotation information to be consulted based on the port user annotation characteristics, and displaying through the display port information.
2. The method of claim 1, wherein before performing recognition conversion on the annotation information to be referred to based on the annotation characteristics of the port user, the method comprises:
obtaining the viewing requirement of a port user;
identifying and searching the annotation information to be searched according to the checking requirement of the port user, and determining the annotation information required to be checked;
determining the annotation feature type according to the annotation features of the port user, and identifying and matching the annotation information required to be checked based on the annotation feature type to obtain matched annotation information to be converted;
and identifying and converting the matched annotation information to be converted based on the port user annotation characteristics.
3. The method of claim 1, wherein the method further comprises:
analyzing the quotation content of the quotation document according to the quotation information to be consulted, and extracting the same-root quotation information set;
analyzing the annotation user information of the same annotation information set to determine the user association degree of the annotation user information and the port user information;
generating different display characteristics based on different user association degrees;
and performing content semantic analysis based on the same-root annotation information set, determining semantic similarity, and performing same-type marking on the annotations with high similarity based on the semantic similarity.
4. The method of claim 1, wherein the method further comprises:
when the display port displays the annotation reply information of the port user, performing semantic recognition on the annotation reply information to obtain reply semantic information;
according to the reply semantic information, displaying the same display characteristics of the semantic similarity meeting the preset requirement;
acquiring annotation user information of the annotation reply information;
determining a reply user relationship according to the annotation user information and the port user information;
and marking the annotation reply information of the port user based on the reply user relationship and the semantic similarity.
5. The method of claim 4, wherein, after displaying the same-display features with semantic similarity meeting preset requirements according to the reply semantic information, the method comprises:
classifying the comment reply information according to the semantic similarity;
determining classification display characteristics based on classification results of the annotation reply information;
and highlighting the semantic similarity lower than a preset threshold.
6. The method of claim 1, wherein the method further comprises:
acquiring a checking demand of an annotation user;
determining checking annotation user information based on the checking requirements of the annotation users, and performing traversal comparison on the multi-document annotation information based on the checking annotation user information to obtain a checking user annotation information set;
analyzing the comment quotation content and the comment information of the checking user comment information set to obtain the user concerned content characteristics and the comment information characteristics;
and generating demand display information to be displayed through the display port information according to the checking user comment information set, the user attention content characteristics and the comment information characteristics.
7. The method of claim 1, wherein inputting the port user's annotation record set into an annotation analysis model to obtain port user annotation characteristics comprises:
according to the annotation record set of the port user, reference content and annotation content are used as input parameters, user annotation characteristics are used as output results, a machine learning model is built, and a training data set is built by using the annotation record set to train and learn the machine learning model;
and performing feature recognition analysis on the reference content and the annotation content to determine annotation type features, performing annotation format and sentence structure sequence recognition processing based on the annotation type features, and determining the port user annotation features.
8. A multi-document based annotation interaction system, the system comprising:
the information acquisition module is used for acquiring multi-document information;
the information identification module is used for identifying multi-document annotation information based on the multi-document information, wherein the multi-document annotation information comprises an annotation position and annotation document reference content;
the information labeling module is used for extracting a source of a annotation user according to the multi-document annotation information, determining the information of the annotation user, and generating a label based on the information of the annotation user to label the multi-document annotation information;
the information determining module is used for acquiring display port information and determining port user information based on the display port information;
the information screening module is used for screening the annotation user information of the multi-document annotation information according to the port user information to obtain annotation information to be consulted, wherein the annotation information to be consulted comprises annotation reply information of the port user and annotation information of non-port users;
the system comprises a characteristic acquisition module, a comment analysis module and a comment analysis module, wherein the characteristic acquisition module is used for acquiring a comment record set of a port user, inputting the comment record set of the port user into a comment analysis model and acquiring the comment characteristics of the port user;
and the information conversion module is used for identifying and converting the annotation information to be consulted based on the port user annotation characteristics and displaying the annotation information through the display port.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211301753.7A CN115659929B (en) | 2022-10-24 | 2022-10-24 | Annotating interaction method and system based on multiple documents |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211301753.7A CN115659929B (en) | 2022-10-24 | 2022-10-24 | Annotating interaction method and system based on multiple documents |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115659929A true CN115659929A (en) | 2023-01-31 |
| CN115659929B CN115659929B (en) | 2023-09-15 |
Family
ID=84991666
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211301753.7A Active CN115659929B (en) | 2022-10-24 | 2022-10-24 | Annotating interaction method and system based on multiple documents |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115659929B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102819531A (en) * | 2011-06-10 | 2012-12-12 | 北大方正集团有限公司 | Cloud reading service system, cloud reading service method and device |
| CN103500158A (en) * | 2013-10-08 | 2014-01-08 | 北京百度网讯科技有限公司 | Method and device for annotating electronic document |
| JP2014139713A (en) * | 2013-01-21 | 2014-07-31 | Mitsubishi Electric Corp | Refereeing result table generating device and refereeing result table generating program |
| CN104391831A (en) * | 2014-11-12 | 2015-03-04 | 武汉传神信息技术有限公司 | Method and system for commenting file contents |
| JP2015138358A (en) * | 2014-01-22 | 2015-07-30 | 日本電気株式会社 | Information processing device, information processing method, and information processing program |
| CN110956023A (en) * | 2018-09-25 | 2020-04-03 | 珠海金山办公软件有限公司 | Comment display method and device |
| US20200160231A1 (en) * | 2018-11-19 | 2020-05-21 | International Business Machines Corporation | Method and System for Using a Multi-Factorial Analysis to Identify Optimal Annotators for Building a Supervised Machine Learning Model |
| US20200272606A1 (en) * | 2019-02-27 | 2020-08-27 | Atlassian Pty. Ltd. | Autonomous redundancy mitigation in knowledge-sharing features of a collaborative work tool |
| CN113392179A (en) * | 2020-12-21 | 2021-09-14 | 腾讯科技（深圳）有限公司 | Text labeling method and device, electronic equipment and storage medium |
| WO2021184574A1 (en) * | 2020-03-20 | 2021-09-23 | 平安国际智慧城市科技股份有限公司 | Document data importing method and apparatus, document data exporting method and apparatus, and storage medium |
-
2022
- 2022-10-24 CN CN202211301753.7A patent/CN115659929B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102819531A (en) * | 2011-06-10 | 2012-12-12 | 北大方正集团有限公司 | Cloud reading service system, cloud reading service method and device |
| JP2014139713A (en) * | 2013-01-21 | 2014-07-31 | Mitsubishi Electric Corp | Refereeing result table generating device and refereeing result table generating program |
| CN103500158A (en) * | 2013-10-08 | 2014-01-08 | 北京百度网讯科技有限公司 | Method and device for annotating electronic document |
| JP2015138358A (en) * | 2014-01-22 | 2015-07-30 | 日本電気株式会社 | Information processing device, information processing method, and information processing program |
| CN104391831A (en) * | 2014-11-12 | 2015-03-04 | 武汉传神信息技术有限公司 | Method and system for commenting file contents |
| CN110956023A (en) * | 2018-09-25 | 2020-04-03 | 珠海金山办公软件有限公司 | Comment display method and device |
| US20200160231A1 (en) * | 2018-11-19 | 2020-05-21 | International Business Machines Corporation | Method and System for Using a Multi-Factorial Analysis to Identify Optimal Annotators for Building a Supervised Machine Learning Model |
| US20200272606A1 (en) * | 2019-02-27 | 2020-08-27 | Atlassian Pty. Ltd. | Autonomous redundancy mitigation in knowledge-sharing features of a collaborative work tool |
| WO2021184574A1 (en) * | 2020-03-20 | 2021-09-23 | 平安国际智慧城市科技股份有限公司 | Document data importing method and apparatus, document data exporting method and apparatus, and storage medium |
| CN113392179A (en) * | 2020-12-21 | 2021-09-14 | 腾讯科技（深圳）有限公司 | Text labeling method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| JAN-CHRISTOPH KLIE等: "The INCEpTION Platform: Machine-Assisted and Knowledge-Oriented Interactive Annotation", PROCEEDINGS OF THE 27TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL LINGUISTICS: SYSTEM DEMONSTRATIONS, pages 5 * |
| SAMUEL DOBBIE等: "Markup: A Web-Based Annotation Tool Powered by Active Learning", FRONTIERS, vol. 3, pages 1 - 9 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115659929B (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100495395C (en) | Data semanticizer | |
| CN110765257A (en) | Intelligent consulting system of law of knowledge map driving type | |
| US7386544B2 (en) | Database search system | |
| CN110956026B (en) | Legal document generation method and device and electronic equipment | |
| US20050182736A1 (en) | Method and apparatus for determining contract attributes based on language patterns | |
| CN112035675A (en) | Medical text labeling method, device, equipment and storage medium | |
| CN111222330B (en) | Chinese event detection method and system | |
| CN112836018A (en) | Method and device for processing emergency plan | |
| CN112182148A (en) | Standard auxiliary compiling method based on full-text retrieval | |
| CN116244410B (en) | Index data analysis method and system based on knowledge graph and natural language | |
| CN113362072B (en) | Wind control data processing method and device, electronic equipment and storage medium | |
| CN111104503A (en) | Construction engineering quality acceptance standard question-answering system and construction method thereof | |
| CN113553419A (en) | Civil aviation knowledge map question-answering system | |
| CN112883202A (en) | Knowledge graph-based multi-component modeling method and system | |
| CN116578703A (en) | Intelligent identification system and method | |
| CN115659929B (en) | Annotating interaction method and system based on multiple documents | |
| CN116644728A (en) | Contract generation method and system based on clause digitization | |
| CN114547342A (en) | College professional intelligent question-answering system and method based on knowledge graph | |
| CN114118098A (en) | Contract review method, equipment and storage medium based on element extraction | |
| CN114676258A (en) | Disease classification intelligent service method based on patient symptom description text | |
| CN117114013B (en) | Semantic annotation method and device based on small sample | |
| CN117332761B (en) | PDF document intelligent identification marking system | |
| CN117436453B (en) | Technical line change trend analysis method and system based on patent data change | |
| CN117931985B (en) | Advanced prompt engineering system, method and electronic equipment of international engineering specification question-answering assistant | |
| US20230419044A1 (en) | Tagging for subject matter or learning schema |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |